The Efficiency of Artificial Recurrent Neural Network (RNN) in Predicting Academic Performance for Students.

This study examines the assessment of two different models, Long Short-Term Memory (LSTM) and Multilayer Perceptron (MLP), specifically in terms of their effectiveness in predicting the academic advancement of students at King Abdulaziz University in Saudi Arabia. The study focuses mostly on courses that include infographics and animated infographics. It employs three main statistics metrics: Symmetric Mean Absolute Percentage Error (SMAPE), Mean Squared Error (MSE), and Mean Absolute Percentage Error (MAPE). The findings of our analysis demonstrate the higher performance of the LSTM model compared to the MLP model in all three-evaluation metrics. More specifically, the LSTM model regularly performs better than the MLP model, with lower values for SMAPE, MSE, and APE. The decreased error metrics in the LSTM column indicate improved overall prediction accuracy in comparison to the MLP model. The study's extensive findings and powerful prediction capabilities signify a substantial advancement in comprehending and utilizing these technologies for educational objectives. This research has ramifications that go beyond academia and can provide real benefits to educators, policymakers, and organizations. This study enhances the continuous endeavors to enhance educational outcomes and student performance by introducing more effective methods for detecting and assisting children who are in danger of expulsion. [ABSTRACT FROM AUTHOR]

Copyright of International Journal of Simulation: Systems, Science & Technology is the property of UK Simulation Society and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)